Artificial Intelligence for Improved Grid Operations and Planning

Argonne researchers are using artificial intelligence to speed up the day-ahead electricity market clearing and real-time operations. The electricity market clearing and grid operations rely on the security constrained unit commitment, or SCUC, which helps grid operators set a schedule for daily and hourly power generation. As the SCUC problem is solved multiple times a day, data accumulates that can be used to discover patterns applicable to solving the next round of problems. To that end, Argonne researchers have developed AI that now can solve a SCUC about 12 times faster than conventional methods. Researchers continue to refine the method, an early version of which was used successfully in tests at Midcontinent Independent System Operator (MISO), overseeing electricity market and delivery across 15 states and one Canadian province.